Skip to main content

AI Router

Route your LLM calls through the AI Router with a single base URL change. Zero vendor lock-in: always run on the best model at the lowest cost for your use case.

Observability

Instrument your code with OpenTelemetry to capture traces, logs, and metrics for every LLM call, agent step, and tool use.

​
AI Router

​
Overview

Agno is a Python framework for building production-ready AI agents with structured workflows, tool integration, and multi-agent orchestration. By connecting Agno to Orq.ai’s AI Router, you get access to 300+ models for your agents with a single configuration change.

​
Key Benefits

Orq.ai’s AI Router enhances your Agno applications with:

Complete Observability

Track every agent interaction, tool use, and model call with detailed traces

Built-in Reliability

Automatic fallbacks, retries, and load balancing for production resilience

Cost Optimization

Real-time cost tracking and spend management across all your AI operations

Multi-Provider Access

Access 300+ LLMs and 20+ providers through a single, unified integration

​
Prerequisites

Before integrating Agno with Orq.ai, ensure you have:
  • An Orq.ai account and API Key
  • Python 3.10 or higher
To setup your API key, see API keys & Endpoints.

​
Installation

pip install agno

​
Configuration

Configure Agno to use Orq.ai’s AI Router via OpenAILike with a custom base_url:
Python
import os
from agno.models.openai.like import OpenAILike

llm = OpenAILike(
    id="openai/gpt-4o",
    api_key=os.getenv("ORQ_API_KEY"),
    base_url="https://api.orq.ai/v2/router",
)
base_url: https://api.orq.ai/v2/router

​
Basic Agent Example

Python
import os
from agno.agent import Agent
from agno.models.openai.like import OpenAILike

llm = OpenAILike(
    id="openai/gpt-4o",
    api_key=os.getenv("ORQ_API_KEY"),
    base_url="https://api.orq.ai/v2/router",
)

agent = Agent(
    model=llm,
    instructions="You are a helpful assistant. Keep responses concise.",
    markdown=True,
)

agent.print_response("Explain machine learning in two sentences.")

​
Agent with Tools

Add tools to your agent for real-world tasks:
Python
import os
from agno.agent import Agent
from agno.models.openai.like import OpenAILike
from agno.tools.yfinance import YFinanceTools

llm = OpenAILike(
    id="openai/gpt-4o",
    api_key=os.getenv("ORQ_API_KEY"),
    base_url="https://api.orq.ai/v2/router",
)

agent = Agent(
    model=llm,
    tools=[YFinanceTools(stock_price=True)],
    instructions="Use tables to display data. Don't include any other text.",
    markdown=True,
)

agent.print_response("What is the stock price of Apple?", stream=True)

​
Agent with Custom Tools

Define your own Python functions as tools:
Python
import os
from agno.agent import Agent
from agno.models.openai.like import OpenAILike

def get_weather(city: str) -> str:
    """Get the current weather for a city."""
    return f"Weather in {city}: Sunny, 22°C."

def convert_currency(amount: float, from_currency: str, to_currency: str) -> str:
    """Convert an amount between currencies."""
    return f"{amount} {from_currency} = {amount * 1.1:.2f} {to_currency} (approximate)"

llm = OpenAILike(
    id="openai/gpt-4o",
    api_key=os.getenv("ORQ_API_KEY"),
    base_url="https://api.orq.ai/v2/router",
)

agent = Agent(
    model=llm,
    tools=[get_weather, convert_currency],
    instructions="Use the available tools to answer questions accurately.",
    markdown=True,
)

agent.print_response("What's the weather in Tokyo and convert 100 USD to EUR?")

​
Multi-Agent Team

Orchestrate multiple specialized agents:
Python
import os
from agno.agent import Agent
from agno.models.openai.like import OpenAILike
from agno.team import Team

llm = OpenAILike(
    id="openai/gpt-4o",
    api_key=os.getenv("ORQ_API_KEY"),
    base_url="https://api.orq.ai/v2/router",
)

researcher = Agent(
    name="Researcher",
    model=llm,
    instructions="You research topics and provide accurate, concise facts.",
    markdown=True,
)

writer = Agent(
    name="Writer",
    model=llm,
    instructions="You take research and turn it into clear, engaging content.",
    markdown=True,
)

team = Team(
    members=[researcher, writer],
    model=llm,
    instructions="Collaborate to produce well-researched, well-written content.",
    markdown=True,
)

team.print_response("Write a short paragraph about renewable energy benefits.")

​
Model Selection

With Orq.ai, you can use any supported model from 20+ providers:
Python
import os
from agno.models.openai.like import OpenAILike

# Use Claude
claude_llm = OpenAILike(
    id="anthropic/claude-sonnet-4-5-20250929",
    api_key=os.getenv("ORQ_API_KEY"),
    base_url="https://api.orq.ai/v2/router",
)

# Use Gemini
gemini_llm = OpenAILike(
    id="google/gemini-2.5-flash",
    api_key=os.getenv("ORQ_API_KEY"),
    base_url="https://api.orq.ai/v2/router",
)

# Use Groq
groq_llm = OpenAILike(
    id="groq/llama-3.3-70b-versatile",
    api_key=os.getenv("ORQ_API_KEY"),
    base_url="https://api.orq.ai/v2/router",
)

​
Observability

​
Installation

pip install opentelemetry-api \
    opentelemetry-sdk \
    "opentelemetry-exporter-otlp-proto-http" \
    openinference-instrumentation-agno

​
Configuring Orq.ai Observability

Set up the tracer provider and instrument Agno before creating any agents: 
import os
from opentelemetry import trace as trace_api
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

exporter = OTLPSpanExporter(
    endpoint="https://api.orq.ai/v2/otel/v1/traces",
    headers={"Authorization": f"Bearer {os.environ['ORQ_API_KEY']}"},
)
tracer_provider = TracerProvider()
tracer_provider.add_span_processor(BatchSpanProcessor(exporter))
trace_api.set_tracer_provider(tracer_provider)

from openinference.instrumentation.agno import AgnoInstrumentor
AgnoInstrumentor().instrument()
The OTEL setup and AgnoInstrumentor().instrument() call must happen before any agent instantiation.

​
Basic Example

import os
from opentelemetry import trace as trace_api
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

exporter = OTLPSpanExporter(
    endpoint="https://api.orq.ai/v2/otel/v1/traces",
    headers={"Authorization": f"Bearer {os.environ['ORQ_API_KEY']}"},
)
tracer_provider = TracerProvider()
tracer_provider.add_span_processor(BatchSpanProcessor(exporter))
trace_api.set_tracer_provider(tracer_provider)

from openinference.instrumentation.agno import AgnoInstrumentor
AgnoInstrumentor().instrument()

from agno.agent import Agent
from agno.models.openai.like import OpenAILike

agent = Agent(
    name="orq-demo",
    model=OpenAILike(
        id="openai/gpt-4o-mini",
        api_key=os.getenv("ORQ_API_KEY"),
        base_url="https://api.orq.ai/v2/router",
    ),
    markdown=True,
)
agent.print_response("Summarize the latest AI news.")